林佳彬，男，1996年生，山东青岛人，中共党员，博士，讲师。2026年1月毕业于美国爱荷华州立大学（Iowa State University）电气与计算机工程专业，获博士学位；2021年获美国南佛罗里达大学（University of South Florida）电气工程硕士学位。2026年入职青岛大学计算机科学技术学院。主要研究方向为强化学习与在线决策、多任务学习、表示学习以及联邦/分布式学习。近年来以第一作者为主在IEEE Transactions on Signal Processing、IEEE Transactions on Signal and Information Processing over Networks、IEEE Control Systems Letters、NeurIPS、ICML等国际知名期刊和会议发表学术论文12篇。获Iowa State University Research Excellence Award（2025）。担任CDC、ACC、ISIT、GameSec、IEEE Transactions on Automatic Control等期刊/会议审稿人。

  研究方向：强化学习与在线决策、多任务学习、表示学习以及联邦/分布式学习。

  联系方式：linjiabinapply@163.com

  办公地点：青岛大学博知楼517

代表性论文

[1] Jiabin Lin, Shana Moothedath, and Namrata Vaswani. Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits, International Conference on Machine Learning (ICML), 2024. (CCF-A)

[2] Jiabin Lin, Shana Moothedath. Provably Efficient Multi-Task Meta Bandit Learning via Shared Representations, Neural Information Processing Systems (NeurIPS), 2025. (CCF-A)

[3] Jiabin Lin, Shana Moothedath, and Tuan Anh Le. Provable Active Multi-Task Representation Learning, IEEE Transactions on Signal Processing, 2025. (SCI IF: 5.8)

[4] Jiabin Lin and Shana Moothedath. Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraint. IEEE Transactions on Signal and Information Processing over Networks, 2025. (SCI IF: 4.9)

[5] Jiabin Lin, Karuna Anna Sajeevan, Bibek Acharya, Shana Moothedath, Ratul Chowdhury. Distributed Stochastic Contextual Bandits for Protein Drug Interaction, International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024. (CCF-B)